Call for Papers
Applied Clinical Informatics Special Topic: Applying Artificial Intelligence in Clinical Decision Support Systems
Overview
This special topic invites original research manuscripts that examine the real-world application of artificial intelligence (AI) within clinical decision support (CDS) systems. We welcome submissions that address the full spectrum of clinical end users—physicians, nurses, pharmacists, and allied health professionals—as well as patients as direct beneficiaries of AI-powered CDS. The emphasis should be on clinical application and measurable outcomes, not theoretical or purely technical contributions.
Organizing Framework
Submissions should demonstrate how AI-powered CDS tools affect one or more of the following domains:
Quality | Patient Safety | Patient Experience | Identification of Populations at Risk |
Improvements in care quality, adherence to evidence-based guidelines, and clinical outcomes. | Effect on alert burden, automation bias, error reduction, and safe deployment of AI tools. | Effects on patient engagement, shared decision-making, and satisfaction. | Effects on detecting at risk populations and resulting outcomes. |
Topics of Interest
We encourage submissions in the following areas (this list is illustrative, not exhaustive):
Clinical Outcomes & Utilization: Studies demonstrating measurable clinical outcomes from AI-enabled CDS across categories of utilization (e.g., diagnostic, therapeutic, preventive). Comparative analyses of AI-powered CDS versus traditional rule-based CDS and their relative effect on patient safety, clinician fatigue, and alert burden.
Evaluation, Validation & Governance: Research on frameworks and methodologies for validating AI-based CDS prior to and during deployment, including governance structures that ensure safety. Studies evaluating bias—comparing model behavior derived from pretraining data against real-world clinical experience.
Explainability & Transparency: Approaches to making AI-driven recommendations interpretable to clinicians and patients, and the effect of explainability on trust, adoption, and clinical decision-making.
Human Factors & Automation Bias: Human factors research examining how clinicians interact with AI-powered CDS, including alert burden, workflow integration, and usability. Studies on automation bias—how user experience level (novice vs. seasoned clinician) influences trust, over-reliance, or distrust of AI-generated recommendations.
Benchmarking & Performance Standards: Development and application of clinical-specific benchmarks curated by domain experts for evaluating AI-CDS performance in real-world settings.
AI CDS & Patient Safety: Investigations into how AI-powered decision support affects patient safety outcomes, including error reduction, near-miss identification, and comparison with legacy CDS systems.
Out of Scope
• Purely theoretical or algorithmic contributions without clinical application or validation.
• Studies lacking a clinical endpoint involving clinicians or patients.
• Technical benchmarking on non-clinical or synthetic datasets without relevance to CDS deployment
Associate Editors
The following individuals will be the guest Associate Editors for this call:
1. David Chestek dchest2@uic.edu (Special Topic Lead)
2. Bhrandon Harris bhrandon@me.com
3. Kate Eisenberg eisenbergkw@gmail.com
4. Gongbo Zhang gz2366@cumc.columbia.edu
5. Esteban Gershanik efgershanik@gmail.com
6. Jakir Hossain Bhuiyan Masud jbmasud@uab.edu
Please address all questions to the Associate Editors.
Instructions to Authors
All submission must be titled “Special Topic AI in CDS: <your actual title here>” without the <>.
Manuscripts can be uploaded at https://mc.manuscriptcentral.com/acij. Instructions for Authors can be found at https://lp.thieme.de/open-access-files/174/author_instructions.pdf.
Deadline for submissions will be Oct 31, 2026 (email the AEs if you need an extension)